Gia Bach Vo

Key Skills

Software

Appen

CloudFactory

Top Subject Matter

Large Language Models (LLM)

Retrieval-Augmented Generation (RAG)

AI alignment

Top Data Types

Text

Image

Top Task Types

RLHF

Fine Tuning

Classification

Freelancer Overview

Machine Learning Engineer – RLHF Specialist. Brings 4+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include HuggingFace, Appen, and Internal. Education includes Bachelor of Science, Hanoi University of Science and Technology (2013) and Master of Science, Hanoi University of Science and Technology (2015). AI-training focus includes data types such as Text and Image and labeling workflows including RLHF, Fine-tuning, and Classification.

Labeling Experience

Machine Learning Engineer – RLHF Specialist

TextRLHF

I integrated RLHF-style structured human feedback processes into LLM pipeline development. I led evaluators while ensuring annotation standards and applied human feedback to improve AI alignment. I implemented and improved data curation workflows for structured model evaluation procedures. • Designed and executed RAG pipelines leveraging RLHF feedback for factual accuracy. • Trained annotation teams to deliver consistent evaluative input on LLM outputs. • Developed human feedback loops for hallucination and bias identification. • Supported enterprise clients with state-of-the-art AI retrieval and labeling workflows.

I integrated RLHF-style structured human feedback processes into LLM pipeline development. I led evaluators while ensuring annotation standards and applied human feedback to improve AI alignment. I implemented and improved data curation workflows for structured model evaluation procedures. • Designed and executed RAG pipelines leveraging RLHF feedback for factual accuracy. • Trained annotation teams to deliver consistent evaluative input on LLM outputs. • Developed human feedback loops for hallucination and bias identification. • Supported enterprise clients with state-of-the-art AI retrieval and labeling workflows.

2023 - 2026

AI Data Trainer & RLHF Specialist

AppenTextFine Tuning

I curated and validated large-scale datasets for supervised fine-tuning and RLHF of language models. I ranked and scored model responses, guiding reward modeling adjustments based on human-labeled quality signals. I collaborated with global annotation teams to standardize data and evaluation criteria for model alignment. • Produced 150K+ labeled examples for LLM fine-tuning. • Evaluated 25K+ outputs, supporting reward model calibration. • Improved prompt templates and dataset structures for more reliable outputs. • Enhanced inter-annotator agreement across multi-timezone teams.

I curated and validated large-scale datasets for supervised fine-tuning and RLHF of language models. I ranked and scored model responses, guiding reward modeling adjustments based on human-labeled quality signals. I collaborated with global annotation teams to standardize data and evaluation criteria for model alignment. • Produced 150K+ labeled examples for LLM fine-tuning. • Evaluated 25K+ outputs, supporting reward model calibration. • Improved prompt templates and dataset structures for more reliable outputs. • Enhanced inter-annotator agreement across multi-timezone teams.

2021 - 2023

AI Data Specialist

ImageClassification

I annotated and validated over half a million multi-modal data samples with a high accuracy rate for enterprise LLM and RAG projects. I developed and standardized guidelines for diverse, multilanguage, and multimodal datasets. I mentored junior annotators and created RAG-ready labeled sets to support advanced embedding pipelines. • Labeled data spanning text, image, and audio modalities for internal projects. • Achieved a 98%+ accuracy rate in annotation tasks. • Authored annotation protocols to ensure dataset consistency and multilingual coverage. • Assisted in developing training modules and reducing label error rates.

I annotated and validated over half a million multi-modal data samples with a high accuracy rate for enterprise LLM and RAG projects. I developed and standardized guidelines for diverse, multilanguage, and multimodal datasets. I mentored junior annotators and created RAG-ready labeled sets to support advanced embedding pipelines. • Labeled data spanning text, image, and audio modalities for internal projects. • Achieved a 98%+ accuracy rate in annotation tasks. • Authored annotation protocols to ensure dataset consistency and multilingual coverage. • Assisted in developing training modules and reducing label error rates.

2018 - 2021

Data Annotation Specialist

CloudfactoryTextClassification

I processed and labeled over 500,000 text datasets in support of machine learning pipeline development and search models. I automated and optimized preprocessing tasks to improve team annotation efficiency and data quality. I collaborated with engineering and annotation teams to deliver production-ready datasets for various client ML projects. • Produced training data for ML and search AI development. • Implemented annotation automation reducing project delivery timelines. • Aligned processed data to project requirements and quality standards. • Facilitated communication between data annotation and engineering functions.

I processed and labeled over 500,000 text datasets in support of machine learning pipeline development and search models. I automated and optimized preprocessing tasks to improve team annotation efficiency and data quality. I collaborated with engineering and annotation teams to deliver production-ready datasets for various client ML projects. • Produced training data for ML and search AI development. • Implemented annotation automation reducing project delivery timelines. • Aligned processed data to project requirements and quality standards. • Facilitated communication between data annotation and engineering functions.

2015 - 2018

Education

Work History